prakartigoel24 / Handwritten-Digit-Recognition-Project

Handwritten-Digit-Recognition-Project

This is a handwritten digit recognizer which uses a Convolutional Neural Network model trained on the popular MNIST dataset to recognize and classify the digits being drawn on the game window that opens when you run the project.

Overview of the Tech-Stack used :

• Languages : Python
• Libraries : Pygame, Matplotlib, Keras, NumPy, OpenCV
• Technology : Deep Learning - CNN

Steps To Run This Project On Your Device :

1. Install python-3.8 (64 bit) or above from 'https://www.python.org/downloads/' and add the PATH to your USER and System Variables under Environment variables.

2. Install VsCode or any other IDE of your choice on your device and make sure to check the add to PATH checkbox.

3. Clone this repository on your system using git clone <repo url> command or download as a Zip folder.

4. Open the project folder in your IDE .

5. Install the necessary libraries by running the pip install -r requirements.txt command on your IDE's terminal.

6. Run the python file named - DrawScreen.py

7. A game window will open and you can draw digits from 0-9 for the model to recognize.

Note : You can make changes in the Model_code.py file to modify the CNN model and then re-train it.

Demo of the project

Source of reference --> (https://youtu.be/L2cAjgc1-bo)